Skip to content

DNN(ONNX): Enabled several OpenCL conformance tests#26053

Merged
asmorkalov merged 2 commits intoopencv:4.xfrom
alexlyulkov:al/opencl-conformance-tests
Aug 27, 2024
Merged

DNN(ONNX): Enabled several OpenCL conformance tests#26053
asmorkalov merged 2 commits intoopencv:4.xfrom
alexlyulkov:al/opencl-conformance-tests

Conversation

@alexlyulkov
Copy link
Copy Markdown
Contributor

@alexlyulkov alexlyulkov commented Aug 21, 2024

The tests also work in 5.x

Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

  • I agree to contribute to the project under Apache 2 License.
  • To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
  • The PR is proposed to the proper branch
  • There is a reference to the original bug report and related work
  • There is accuracy test, performance test and test data in opencv_extra repository, if applicable
    Patch to opencv_extra has the same branch name.
  • The feature is well documented and sample code can be built with the project CMake

@alexlyulkov alexlyulkov requested a review from asmorkalov August 21, 2024 09:47
@opencv-alalek
Copy link
Copy Markdown
Contributor

Please add "DNN(ONNX): " prefix due to misleading of current commit message.

@asmorkalov asmorkalov changed the title Enabled several OpenCL conformance tests DNN(ONNX): Enabled several OpenCL conformance tests Aug 21, 2024
@asmorkalov
Copy link
Copy Markdown
Contributor

I tested the patch with integrated Intel GFX (Intel(R) Core(TM) i3-7100U CPU @ 2.40GHz):

./bin/opencv_test_dnn --gtest_output=xml:./test_dnn.xml --gtest_filter=Test_ONNX_conformance*
...
[  FAILED  ] 15 tests, listed below:
[  FAILED  ] Test_ONNX_conformance.Layer_Test/test_logsoftmax_large_number_OCV_OCL_FP16, where GetParam() = (test_logsoftmax_large_number, OCV/OCL_FP16)
[  FAILED  ] Test_ONNX_conformance.Layer_Test/test_logsoftmax_large_number_expanded_OCV_OCL_FP16, where GetParam() = (test_logsoftmax_large_number_expanded, OCV/OCL_FP16)
[  FAILED  ] Test_ONNX_conformance.Layer_Test/test_pow_OCV_OCL_FP16, where GetParam() = (test_pow, OCV/OCL_FP16)
[  FAILED  ] Test_ONNX_conformance.Layer_Test/test_reduce_prod_default_axes_keepdims_example_OCV_OCL_FP16, where GetParam() = (test_reduce_prod_default_axes_keepdims_example, OCV/OCL_FP16)
[  FAILED  ] Test_ONNX_conformance.Layer_Test/test_reduce_prod_default_axes_keepdims_random_OCV_OCL_FP16, where GetParam() = (test_reduce_prod_default_axes_keepdims_random, OCV/OCL_FP16)
[  FAILED  ] Test_ONNX_conformance.Layer_Test/test_reduce_prod_do_not_keepdims_random_OCV_OCL_FP16, where GetParam() = (test_reduce_prod_do_not_keepdims_random, OCV/OCL_FP16)
[  FAILED  ] Test_ONNX_conformance.Layer_Test/test_reduce_prod_keepdims_random_OCV_OCL_FP16, where GetParam() = (test_reduce_prod_keepdims_random, OCV/OCL_FP16)
[  FAILED  ] Test_ONNX_conformance.Layer_Test/test_reduce_prod_negative_axes_keepdims_random_OCV_OCL_FP16, where GetParam() = (test_reduce_prod_negative_axes_keepdims_random, OCV/OCL_FP16)
[  FAILED  ] Test_ONNX_conformance.Layer_Test/test_reduce_sum_square_default_axes_keepdims_random_OCV_OCL_FP16, where GetParam() = (test_reduce_sum_square_default_axes_keepdims_random, OCV/OCL_FP16)
[  FAILED  ] Test_ONNX_conformance.Layer_Test/test_reduce_sum_square_do_not_keepdims_random_OCV_OCL_FP16, where GetParam() = (test_reduce_sum_square_do_not_keepdims_random, OCV/OCL_FP16)
[  FAILED  ] Test_ONNX_conformance.Layer_Test/test_reduce_sum_square_keepdims_random_OCV_OCL_FP16, where GetParam() = (test_reduce_sum_square_keepdims_random, OCV/OCL_FP16)
[  FAILED  ] Test_ONNX_conformance.Layer_Test/test_reduce_sum_square_negative_axes_keepdims_random_OCV_OCL_FP16, where GetParam() = (test_reduce_sum_square_negative_axes_keepdims_random, OCV/OCL_FP16)
[  FAILED  ] Test_ONNX_conformance.Layer_Test/test_softmax_large_number_OCV_OCL_FP16, where GetParam() = (test_softmax_large_number, OCV/OCL_FP16)
[  FAILED  ] Test_ONNX_conformance.Layer_Test/test_softmax_large_number_expanded_OCV_OCL_FP16, where GetParam() = (test_softmax_large_number_expanded, OCV/OCL_FP16)
[  FAILED  ] Test_ONNX_conformance.Layer_Test/test_tan_OCV_OCL_FP16, where GetParam() = (test_tan, OCV/OCL_FP16)

@asmorkalov asmorkalov added category: dnn (onnx) ONNX suport issues in DNN module test labels Aug 22, 2024
@asmorkalov
Copy link
Copy Markdown
Contributor

asmorkalov commented Aug 26, 2024

@alexlyulkov friendly reminder.

@asmorkalov asmorkalov added this to the 4.11.0 milestone Aug 27, 2024
@asmorkalov
Copy link
Copy Markdown
Contributor

Tested with Intel(R) Core(TM) i3-7100U and integrated graphics.

@asmorkalov asmorkalov self-assigned this Aug 27, 2024
@asmorkalov asmorkalov merged commit 766bad0 into opencv:4.x Aug 27, 2024
@asmorkalov asmorkalov mentioned this pull request Aug 27, 2024
thewoz pushed a commit to CobbsLab/OPENCV that referenced this pull request Feb 13, 2025
…e-tests

DNN(ONNX): Enabled several OpenCL conformance tests opencv#26053

The tests also work in 5.x

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

category: dnn (onnx) ONNX suport issues in DNN module test

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants